ERNIE X1.1: benchmark results
Provider: Baidu. Access: API.
Aggregate Rating 1652 ± 32, rank #606 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE General (September 2025) - Hallucination Control | 78.78 | Score | 91.7 |
| SuperCLUE General (September 2025) - Agent | 78.33 | Score | 88.9 |
| SuperCLUE General (September 2025) - Precise Instruction Following | 64.91 | Score | 83.3 |
| SuperCLUE-CPIF - Overall | 75.9 | Score | 71.4 |
| SuperCLUE General (September 2025) - Overall | 60.33 | Score | 66.7 |
| LLM2014 Logic 2025-10 | 31.95 | Median Score | 38.8 |
| LLM2014 Logic 2025-09 | 30.61 | Median Score | 37.8 |
| SuperCLUE General (September 2025) - Code Generation | 53.86 | Score | 36.1 |
| SuperCLUE General (September 2025) - Math Reasoning | 52.45 | Score | 36.1 |
| SuperCLUE General (September 2025) - Science Reasoning | 33.62 | Score | 20.8 |
Interactive version: theaggregate.ai/model?slug=ernie-x1-1 · How It Works · Data refreshed daily, snapshot 2026-11-08.